Reproduce “Understanding and Enhancing Backdoor Persistency in LLM Agent Post-Training” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Qiusi Zhan, Nian Lyu, Stephanie Ding, Arnav Mehta, Chris Canal, Connor Tabarrok, Xander Davies, Daniel Kang
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.